-
Hi,
Thank you for the sharing. I replaced the DETR's encoder MultiHeadAtten with SimA, it works pretty well. I am wondering is it possible to replace the cross attention in decoder? If so, any clu…
-
Hello
first of all thank you for your great work
i would like to extract the cross attention maps to visualize spatial attention in a synchronized way to my images (during training on my val and a…
-
(base) pengshan@MacBook-Pro comfyui % python main.py
Total VRAM 16384 MB, total RAM 16384 MB
pytorch version: 2.4.1
Set vram state to: SHARED
Device: mps
Using sub quadratic optimization for cros…
-
I'm trying to run the model on MacBook Pro M1 Max
Getting this error:
```
The config attributes {'decay': 0.9999, 'inv_gamma': 1.0, 'min_decay': 0.0, 'optimization_step': 37000, 'power': 0.666…
-
when I run "python src/eval.py --dataset_path --batch_size --mixed_precision fp16 --output_dir --save_name --num_workers_test --sketch_cond_rate 0.2 --dataset --start_cond_rate 0.0 --test_order …
-
First and foremost, I would like to express my appreciation for the outstanding work you have done in this field. Your insights have had a significant impact on my research, and I greatly admire your …
-
Dear Author
I am trying to locate the section of the code that handles the cross-attention layer between text embedding and visual embedding. Could you please guide me to the relevant part of the c…
-
Thank you for your implementation of SAMI's training code. It has been incredibly helpful for me!
However,I have a question regarding the pretraining process. In forward preprocess of the [MaeDeco…
-
I am confusing about the text2music config. It seems like in `config/model/lm/default.yaml` the `cross_attention=False` and I didn't see any overwrite in `musicgen_lm.yaml` but in the output of the fu…
-
### Feature Idea
When running comfyui standalone build for windows cpu version, the utilization of all cpu cores are not implemented for torch. Adding few lines of code to ComfyUI/comfy/utils.py or m…